College of Information and Computer Sciences · UMass Amherst
The typical smartphone comes equipped with a plethora of sensors for monitoring activity, speech patterns, social interactions, and location. In addition, mobile accessories such as wearable wristbands now enable routine and continuous monitoring of a host of physiological signals (e.g., heart rate, respiratory rate, oxygen saturation, and others). In conjunction, these sensors can enable higher-order inferences about more complex human activities and behavioral states (e.g., activity patterns, stress, sleep, social interactions, etc.). Such ubiquitous sensing in daily life, referred to as mobile health sensing, promises to revolutionize our understanding of human activities and health conditions.
This course is a hands-on introduction to personal health sensing through mobile phones and on-body sensors. This course counts as a CS Elective toward the CS major (BA/BS). 3 credits.
Fitness gadgets such as Fitbit, Apple Watch, Android Wear, Oura ring, and smartphone apps such as RunKeeper calculate activity patterns, calories burned each day, track sleep patterns, and compute heart rate. We will learn how to build the computational elements for developing such applications by leveraging various sensors on smartphones. At the end of the class, you will have understood how these devices monitor activity patterns, heart rate, conversation patterns, and your mobility patterns. This is a hands-on course where students learn by doing!
COMPSCI 187 (Data Structures) or equivalent, or instructor's approval. Please note that this is a programming-heavy class, so a solid programming background is required. All programming assignments are in Python, so programming experience with Python is strongly recommended. If you have no prior experience in Python but have substantial programming experience, we expect that you are able to teach yourself the basics of Python to get up to speed.
There is no textbook for the course; course notes are available online.
The course will include coverage of the following topics:
Additional office hours are available on request.
The class has substantial emphasis on practical systems development.
| Component | Weight |
|---|---|
| Programming assignments (3) | 48% |
| Final project | 20% |
| Quizzes (6) | 15% |
| Midterm (1) | 15% |
| Class participation & attendance | 2% |
We will provide support (including shell code) for projects that will be in Python. There will be three assignments in the area of human activity recognition using sensor data from wearables and mobile phones.
In the final project, students can use what they have learnt in class as well as the classifiers that they have developed in assignments to develop their own application. Students will be expected to use a broader range of sensors (e.g., audio, gyroscope, accelerometer, barometer, GPS, etc.) and classification tools learnt in class. Scaffolding to collect data and extract features will be provided as needed.
There will be 6–8 in-class quizzes (closed book), each about 20 minutes. These will cover topics from your programming assignments as well as topics covered in lectures.
There will be one midterm that covers material covered in class.
The University of Massachusetts Amherst is committed to providing an equal educational opportunity for all students. If you have a documented physical, psychological, or learning disability on file with Disability Services (DS), you may be eligible for reasonable academic accommodations to help you succeed in this course. If you have a documented disability that requires an accommodation, please notify the instructor within the first two weeks of the semester so that appropriate arrangements can be made.
Since the integrity of the academic enterprise of any institution of higher education requires honesty in scholarship and research, academic honesty is required of all students at the University of Massachusetts Amherst. Academic dishonesty is prohibited in all programs of the University. Academic dishonesty includes but is not limited to: cheating, fabrication, plagiarism, and facilitating dishonesty. Appropriate sanctions may be imposed on any student who has committed an act of academic dishonesty. Any person who has reason to believe that a student has committed academic dishonesty should bring such information to the attention of the appropriate course instructor as soon as possible. Since students are expected to be familiar with this policy and the commonly accepted standards of academic integrity, ignorance of such standards is not normally sufficient evidence of lack of intent. See the university academic integrity policy.